submission_id: cgato-thesalt-rp-l3-8b-d_3430_v1
developer_uid: c.gato
status: inactive
model_repo: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.7.2
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\\r', '\\r\n', '\n\n', 'You:'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}
reward_formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
timestamp: 2024-07-03T22:48:22+00:00
model_name: cgato-thesalt-rp-l3-8b-d_3430_v1
model_group: cgato/TheSalt-RP-L3-8b-D
num_battles: 12964
num_wins: 6660
celo_rating: 1199.7
propriety_score: 0.7229247730220493
propriety_total_count: 6168.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030294016.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: cgato-thesalt-rp-l3-8b-d_3430_v1
ineligible_reason: None
language_model: cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.7.2
model_size: 8B
reward_model: ChaiML/reward_gpt2_medium_preference_24m_e2
us_pacific_date: 2024-07-03
win_ratio: 0.513730330145017
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: Downloaded to shared memory in 43.504s
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:02, 116.80it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:02, 96.19it/s] Loading 0: 12%|█▏ | 35/291 [00:00<00:02, 99.00it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:02, 100.44it/s] Loading 0: 20%|█▉ | 57/291 [00:00<00:02, 101.43it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:02, 92.11it/s] Loading 0: 28%|██▊ | 81/291 [00:00<00:02, 102.96it/s] Loading 0: 32%|███▏ | 92/291 [00:01<00:03, 54.76it/s] Loading 0: 35%|███▌ | 102/291 [00:01<00:03, 60.06it/s] Loading 0: 38%|███▊ | 111/291 [00:01<00:02, 64.85it/s] Loading 0: 41%|████ | 120/291 [00:01<00:02, 69.95it/s] Loading 0: 45%|████▍ | 130/291 [00:01<00:02, 74.52it/s] Loading 0: 48%|████▊ | 139/291 [00:01<00:01, 78.06it/s] Loading 0: 51%|█████ | 148/291 [00:01<00:01, 80.11it/s] Loading 0: 54%|█████▍ | 158/291 [00:01<00:01, 82.75it/s] Loading 0: 58%|█████▊ | 170/291 [00:02<00:01, 92.65it/s] Loading 0: 62%|██████▏ | 180/291 [00:02<00:01, 92.46it/s] Loading 0: 65%|██████▌ | 190/291 [00:02<00:02, 49.45it/s] Loading 0: 69%|██████▉ | 201/291 [00:02<00:01, 57.64it/s] Loading 0: 73%|███████▎ | 211/291 [00:02<00:01, 63.31it/s] Loading 0: 76%|███████▌ | 221/291 [00:02<00:01, 69.01it/s] Loading 0: 80%|████████ | 234/291 [00:03<00:00, 82.59it/s] Loading 0: 85%|████████▍ | 246/291 [00:03<00:00, 88.84it/s] Loading 0: 88%|████████▊ | 256/291 [00:03<00:00, 87.16it/s] Loading 0: 91%|█████████▏| 266/291 [00:03<00:00, 90.25it/s] Loading 0: 96%|█████████▌| 278/291 [00:03<00:00, 97.55it/s] Loading 0: 99%|█████████▉| 289/291 [00:09<00:00, 5.77it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: quantized model in 26.000s
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.7.2 in 69.504s
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-3430-v1
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-3430-v1/config.json
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-3430-v1/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-3430-v1/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-3430-v1/tokenizer.json
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-3430-v1/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: Saving duration: 0.495s
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 22.886s
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3430-v1_reward
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3430-v1_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3430-v1_reward/config.json
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3430-v1_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3430-v1_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3430-v1_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3430-v1_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3430-v1_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer completed after 114.92s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-3430-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.84s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-3430-v1
Waiting for inference service cgato-thesalt-rp-l3-8b-d-3430-v1 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-3430-v1 ready after 50.287317752838135s
Pipeline stage ISVCDeployer completed in 57.05s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1301052570343018s
Received healthy response to inference request in 1.2884161472320557s
Received healthy response to inference request in 1.2958505153656006s
Received healthy response to inference request in 1.3074302673339844s
Received healthy response to inference request in 1.2537822723388672s
5 requests
0 failed requests
5th percentile: 1.2607090473175049
10th percentile: 1.2676358222961426
20th percentile: 1.281489372253418
30th percentile: 1.2899030208587647
40th percentile: 1.2928767681121827
50th percentile: 1.2958505153656006
60th percentile: 1.300482416152954
70th percentile: 1.3051143169403077
80th percentile: 1.471965265274048
90th percentile: 1.801035261154175
95th percentile: 1.965570259094238
99th percentile: 2.097198257446289
mean time: 1.4551168918609618
Pipeline stage StressChecker completed in 7.94s
cgato-thesalt-rp-l3-8b-d_3430_v1 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_3430_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics